• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.493-500
• /
• 2021

In this paper, we propose the development of deep learning structure to improve quality of polygonal containers. The deep learning structure consists of a convolution layer, a bottleneck layer, a fully connect layer, and a softmax layer. The convolution layer is a layer that obtains a feature image by performing a convolution 3x3 operation on the input image or the feature image of the previous layer with several feature filters. The bottleneck layer selects only the optimal features among the features on the feature image extracted through the convolution layer, reduces the channel to a convolution 1x1 ReLU, and performs a convolution 3x3 ReLU. The global average pooling operation performed after going through the bottleneck layer reduces the size of the feature image by selecting only the optimal features among the features of the feature image extracted through the convolution layer. The fully connect layer outputs the output data through 6 fully connect layers. The softmax layer multiplies and multiplies the value between the value of the input layer node and the target node to be calculated, and converts it into a value between 0 and 1 through an activation function. After the learning is completed, the recognition process classifies non-circular glass bottles by performing image acquisition using a camera, measuring position detection, and non-circular glass bottle classification using deep learning as in the learning process. In order to evaluate the performance of the deep learning structure to improve quality of polygonal containers, as a result of an experiment at an authorized testing institute, it was calculated to be at the same level as the world's highest level with 99% good/defective discrimination accuracy. Inspection time averaged 1.7 seconds, which was calculated within the operating time standards of production processes using non-circular machine vision systems. Therefore, the effectiveness of the performance of the deep learning structure to improve quality of polygonal containers proposed in this paper was proven.

• Journal of Appropriate Technology
• /
• v.7 no.2
• /
• pp.162-171
• /
• 2021

The Korean government proposed the K-SDGs in 2019 to promote the UN SDGs, but the role and tasks of science and technology, an important means of implementing the SDGs, have not been materialized. Accordingly, the role of science and technology ODA for the SDGs was established through the Ministry of Science and ICT's policy research project 'Science and Technology ODA Promotion Roadmap for Spreading the New Southern Policy and Realizing the 2030 SDGs'. In addition, goals, strategies, and core tasks for the next 10 years were derived in 10 fields such as water, climate change, energy, and ICT. In this paper, we analyze 30 key tasks of the ODA promotion roadmap for science and technology for the realization of SDGs, and propose mid- and short-term tasks and implementation plans for effective roadmap promotion. Among the key tasks in each field, four common elements were derived: ICT/smartization, a global problem-solving center, cooperation/communication platform, and business model/startup support platform/living lab that can create and integrate roadmap implementation conditions. In addition, the four mid- and short-term tasks, 1) Establishment of science and technology ODA network, 2) Establishment of living lab business platform linked to start-up support business, 3) Local smartization of recipient countries, and 4) Expand and secure sustainability of global problem-solving centers, were set in relation to the implementation of the detailed roadmap. For the derived mid- and short-term tasks, detailed implementation plans based on the ICTization of global problem-solving centers were presented. The implementation of the mid- and short-term tasks presented in this paper can contribute to the more effective achievement of the science and technology ODA roadmap, and it is expected that Korea's implementation of SDGs will also achieve high performance.

• Journal of IKEEE
• /
• v.27 no.1
• /
• pp.116-121
• /
• 2023

In this paper, we develop a deep learning structure for a complex microbial incubator that applies deep learning prediction result information. The proposed complex microbial incubator consists of pre-processing of complex microbial data, conversion of complex microbial data structure, design of deep learning network, learning of the designed deep learning network, and GUI development applied to the prototype. In the complex microbial data preprocessing, one-hot encoding is performed on the amount of molasses, nutrients, plant extract, salt, etc. required for microbial culture, and the maximum-minimum normalization method for the pH concentration measured as a result of the culture and the number of microbial cells to preprocess the data. In the complex microbial data structure conversion, the preprocessed data is converted into a graph structure by connecting the water temperature and the number of microbial cells, and then expressed as an adjacency matrix and attribute information to be used as input data for a deep learning network. In deep learning network design, complex microbial data is learned by designing a graph convolutional network specialized for graph structures. The designed deep learning network uses a cosine loss function to proceed with learning in the direction of minimizing the error that occurs during learning. GUI development applied to the prototype shows the target pH concentration (3.8 or less) and the number of cells (10⁸ or more) of complex microorganisms in an order suitable for culturing according to the water temperature selected by the user. In order to evaluate the performance of the proposed microbial incubator, the results of experiments conducted by authorized testing institutes showed that the average pH was 3.7 and the number of cells of complex microorganisms was 1.7 × 10⁸. Therefore, the effectiveness of the deep learning structure for the complex microbial incubator applying the deep learning prediction result information proposed in this paper was proven.

• Journal of IKEEE
• /
• v.27 no.1
• /
• pp.122-126
• /
• 2023

In this paper, a control system for a complex microbial incubator was proposed. The proposed control system consists of a control unit, a communication unit, a power supply unit, and a control system of the complex microbial incubator. The controller of the complex microbial incubator is designed and manufactured to convert analog signals and digital signals, and control signals of sensors such as displays using LCD panels, water level sensors, temperature sensors, and pH concentration sensors. The water level sensor used is designed and manufactured to enable accurate water level measurement by using the IR laser method with excellent linearity in order to solve the problem that existing water level sensors are difficult to measure due to foreign substances such as bubbles. The temperature sensor is designed and used so that it has high accuracy and no cumulative resistance error by measuring using the thermal resistance principle. The communication unit consists of two LAN ports and one RS-232 port, and is designed and manufactured to transmit signals such as LCD panel, PCT panel, and load cell controller used in the complex microbial incubator to the control unit. The power supply unit is designed and manufactured to supply power by configuring it with three voltage supply terminals such as 24V, 12V and 5V so that the control unit and communication unit can operate smoothly. The control system of the complex microbial incubator uses PLC to control sensor values such as pH concentration sensor, temperature sensor, and water level sensor, and the operation of circulation pump, circulation valve, rotary pump, and inverter load cell used for cultivation. In order to evaluate the performance of the control system of the proposed complex microbial incubator, the result of the experiment conducted by the accredited certification body showed that the range of water level measurement sensitivity was -0.41mm~1.59mm, and the range of change in water temperature was ±0.41℃, which is currently commercially available. It was confirmed that the product operates with better performance than the performance of the products. Therefore, the effectiveness of the control system of the complex microbial incubator proposed in this paper was demonstrated.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.464-471
• /
• 2023

In this paper, we propose a method to reduce age distortion in facial expression image generation using StyleGAN Encoder. The facial expression image generation process first creates a face image using StyleGAN Encoder, and changes the expression by applying the learned boundary to the latent vector using SVM. However, when learning the boundary of a smiling expression, age distortion occurs due to changes in facial expression. The smile boundary created in SVM learning for smiling expressions includes wrinkles caused by changes in facial expressions as learning elements, and it is determined that age characteristics were also learned. To solve this problem, the proposed method calculates the correlation coefficient between the smile boundary and the age boundary and uses this to introduce a method of adjusting the age boundary at the smile boundary in proportion to the correlation coefficient. To confirm the effectiveness of the proposed method, the results of an experiment using the FFHQ dataset, a publicly available standard face dataset, and measuring the FID score are as follows. In the smile image, compared to the existing method, the FID score of the smile image generated by the ground truth and the proposed method was improved by about 0.46. In addition, compared to the existing method in the smile image, the FID score of the image generated by StyleGAN Encoder and the smile image generated by the proposed method improved by about 1.031. In non-smile images, compared to the existing method, the FID score of the non-smile image generated by the ground truth and the method proposed in this paper was improved by about 2.25. In addition, compared to the existing method in non-smile images, it was confirmed that the FID score of the image generated by StyleGAN Encoder and the non-smile image generated by the proposed method improved by about 1.908. Meanwhile, as a result of estimating the age of each generated facial expression image and measuring the estimated age and MSE of the image generated with StyleGAN Encoder, compared to the existing method, the proposed method has an average age of about 1.5 in smile images and about 1.63 in non-smile images. Performance was improved, proving the effectiveness of the proposed method.

• Journal of Internet Computing and Services
• /
• v.14 no.5
• /
• pp.1-10
• /
• 2013

RFID(Radio Frequency Identification) system is non-contact identification technology. A basic RFID system consists of a reader, and a set of tags. RFID tags can be divided into active and passive tags. Active tags with power source allows their own operation execution and passive tags are small and low-cost. So passive tags are more suitable for distribution industry than active tags. A reader processes the information receiving from tags. RFID system achieves a fast identification of multiple tags using radio frequency. RFID systems has been applied into a variety of fields such as distribution, logistics, transportation, inventory management, access control, finance and etc. To encourage the introduction of RFID systems, several problems (price, size, power consumption, security) should be resolved. In this paper, we proposed an algorithm to significantly alleviate the collision problem caused by simultaneous responses of multiple tags. In the RFID systems, in anti-collision schemes, there are three methods: probabilistic, deterministic, and hybrid. In this paper, we introduce ALOHA-based protocol as a probabilistic method, and Tree-based protocol as a deterministic one. In Aloha-based protocols, time is divided into multiple slots. Tags randomly select their own IDs and transmit it. But Aloha-based protocol cannot guarantee that all tags are identified because they are probabilistic methods. In contrast, Tree-based protocols guarantee that a reader identifies all tags within the transmission range of the reader. In Tree-based protocols, a reader sends a query, and tags respond it with their own IDs. When a reader sends a query and two or more tags respond, a collision occurs. Then the reader makes and sends a new query. Frequent collisions make the identification performance degrade. Therefore, to identify tags quickly, it is necessary to reduce collisions efficiently. Each RFID tag has an ID of 96bit EPC(Electronic Product Code). The tags in a company or manufacturer have similar tag IDs with the same prefix. Unnecessary collisions occur while identifying multiple tags using Query Tree protocol. It results in growth of query-responses and idle time, which the identification time significantly increases. To solve this problem, Collision Tree protocol and M-ary Query Tree protocol have been proposed. However, in Collision Tree protocol and Query Tree protocol, only one bit is identified during one query-response. And, when similar tag IDs exist, M-ary Query Tree Protocol generates unnecessary query-responses. In this paper, we propose Adaptive M-ary Query Tree protocol that improves the identification performance using m-bit recognition, collision information of tag IDs, and prediction technique. We compare our proposed scheme with other Tree-based protocols under the same conditions. We show that our proposed scheme outperforms others in terms of identification time and identification efficiency.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.21 no.6
• /
• pp.670-680
• /
• 2010

A low power single-chip CMOS receiver for 60 GHz mobile application are proposed in this paper. The single-chip receiver consists of a 4-stage current re-use LNA with under 4 dB NF, Cgs compensating resistive mixer with -9.4 dB conversion gain, Ka-band low phase noise VCO with -113 dBc/Hz phase noise at 1 MHz offset from 26.89 GHz, high-suppression frequency doubler with -0.45 dB conversion gain, and 2-stage current re-use drive amplifier. The size of the fabricated receiver using a standard 0.13 ${\mu}m$ CMOS technology is 2.67 mm$\times$0.75 mm including probing pads. An RF bandwidth is 6.2 GHz, from 55 to 61.2 GHz and an LO tuning range is 7.14 GHz, from 48.45 GHz to 55.59 GHz. The If bandwidth is 5.25 GHz(4.75~10 GHz) The conversion gain and input P1 dB are -9.5 dB and -12.5 dBm, respectively, at RF frequency of 59 GHz. The proposed single-chip receiver describes very good noise performances and linearity with very low DC power consumption of only 21.9 mW.

• Journal of Broadcast Engineering
• /
• v.10 no.1 s.26
• /
• pp.43-56
• /
• 2005

In the existing broadcasting environment, it is not easy to serve the bi-directional service between a broadcasting server and a TV audience. In the uni-directional broadcasting environments, almost TV programs are scheduled depending on the viewers' popular watching time, and the advertisement contents in these TV programs are mainly arranged by the popularity and the ages of the audience. The audiences make an effort to sort and select their favorite programs. However, the advertisement programs which support the TV program the audience want are not served to the appropriate audiences efficiently. This randomly provided advertisement contents can occur to the audiences' indifference and avoidance. In this paper, we propose the target advertisement service for the appropriate distribution of the advertisement contents. The proposed target advertisement service estimates the audience's profile without any issuing the private information and provides the target-advertised contents by using his/her estimated profile. For the experimental results, we used the real audiences' TV usage history such as the ages, fonder and time of the programs from AC Neilson Korea. And we show the accuracy of the proposed target advertisement service algorithm. NDS (Normalized Distance Sum) and the Vector correlation method, and implementation of our target advertisement service system.

• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.95-105
• /
• 2013

Recently, SME's Collaboration activities have become one of a vital factor for sustaining competitive edge. This is because of the rapidly changing and competitive market environment, and also to leverage performance by overcoming obstacles of having limited internal resources. Discussing about the effects and relationships of the firm's collaboration activities and its outputs are not new. However, as ICT and various technologies have been diffused into the traditional industries, boundaries and practice capabilities within the industries are becoming ambiguous. Thus contents of the products/services and their development methods are also go and come over the industries. Although many researchers suggested the relations of SME's collaboration activities and innovation performances, most of the previous literatures are focusing on broad perspectives of firm's environmental factors rather than considering various SME's idiosyncrasy factors such as their major product and customer types at once. Therefore, the purpose of this paper is to analyze how SME(Small Medium Enterprise)'s external collaboration activities by their idiosyncrasy act as an input to types of innovation performance. In order to analyze collaboration effects in detail, we defined factors that can represent the SME's business environment - Perceived importance of using external resources, Perceived importance of external partnership, Collaboration and Collaboration levels of Major Product types, Customer types and lastly the Firm Sizes. We have also specifically divided the performance of innovation types as product innovation and process innovation based on existing research. In this study, the empirical analysis is based on Probit Regression Model to observe the correlations with the impact of each SME's business environment and their activities. For the empirical data, 497 samples were collected which, this sample data was extracted from the 'Korean Open Innovation Survey' performed by ETRI(Korean Electronics Telecommunications Research Institute) in 2010. As a result, empirical test results indicated that the impact of collaboration varies depend on the innovation types (Product and Process Innovation). The Impact of the collaboration level for the product innovation tend to be more effective when SMEs are developing for a final product, targeting on for individual customers (B2C). But on the other hand, the analysis result of the Process innovation tend to be higher than the product innovation, when SMEs are developing raw materials for their partners or to other firms targeting on for manufacturing industries(B2B). Also perceived importance of using external resources has effected to both product and process innovation performance. But Perceived importance of external partnership was statistically insignificant. Interesting finding was that the service product has negative effects on for the process innovation performance. And Relationship between size of the firms and their external collaboration activities with their performance of the innovations indicated that the bigger firms(over 100 of employees) tend to have better for both product and process innovations. Finally, implications of the results can be suggested as performance of innovation can be varied depends on firm's unique business idiosyncrasy as well as levels of external collaboration activities. The Implication of this research can be considered for firms in selecting an appropriate strategy as well as for policy makers.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.47-60
• /
• 2010

Most of the researches about classification usually have used kNN(k-Nearest Neighbor), SVM(Support Vector Machine), which are known as learn-based model, and Bayesian classifier, NNA(Neural Network Algorithm), which are known as statistics-based methods. However, there are some limitations of space and time when classifying so many web pages in recent internet. Moreover, most studies of classification are using uni-gram feature representation which is not good to represent real meaning of words. In case of Korean web page classification, there are some problems because of korean words property that the words have multiple meanings(polysemy). For these reasons, LSA(Latent Semantic Analysis) is proposed to classify well in these environment(large data set and words' polysemy). LSA uses SVD(Singular Value Decomposition) which decomposes the original term-document matrix to three different matrices and reduces their dimension. From this SVD's work, it is possible to create new low-level semantic space for representing vectors, which can make classification efficient and analyze latent meaning of words or document(or web pages). Although LSA is good at classification, it has some drawbacks in classification. As SVD reduces dimensions of matrix and creates new semantic space, it doesn't consider which dimensions discriminate vectors well but it does consider which dimensions represent vectors well. It is a reason why LSA doesn't improve performance of classification as expectation. In this paper, we propose new LSA which selects optimal dimensions to discriminate and represent vectors well as minimizing drawbacks and improving performance. This method that we propose shows better and more stable performance than other LSAs' in low-dimension space. In addition, we derive more improvement in classification as creating and selecting features by reducing stopwords and weighting specific values to them statistically.